Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    situations or events that happen suddenly or unexpectedly

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sudden changes or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fect
    -0.65
    agra
    -0.63
     histories
    -0.62
     discipline
    -0.60
     liter
    -0.58
     divisions
    -0.58
     mag
    -0.57
     belts
    -0.57
     atmosp
    -0.57
     attachments
    -0.56
    POSITIVE LOGITS
    forth
    0.81
    nir
    0.76
    adays
    0.74
    essage
    0.72
     THERE
    0.70
    soever
    0.70
    ilot
    0.69
    Ëľ
    0.69
    here
    0.69
    Db
    0.68
    Act Density 0.034%

    No Known Activations